{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,12]],"date-time":"2026-11-12T08:49:58Z","timestamp":1794473398655,"version":"4.9.1"},"reference-count":48,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T00:00:00Z","timestamp":1763424000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100012331","name":"Agentschap Innoveren en Ondernemen","doi-asserted-by":"publisher","award":["HBC.2021.1052"],"award-info":[{"award-number":["HBC.2021.1052"]}],"id":[{"id":"10.13039\/100012331","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Plant Sci."],"abstract":"<jats:p>\n                    As of today, pest insects such as thrips and whiteflies cause the loss of 20% - 40% of the global agricultural yield. To reduce chemical pesticide use while maintaining high-quality horticultural standards, early detection of pest infestations is essential. Although AI-assisted pest monitoring systems using sticky trap images exist today, none currently enable effective species-level detection of thrips and\/or whiteflies. However, early species-level identification would allow for more targeted, species-specific control strategies, leading to reduced, localized, and more efficient pesticide application. Therefore, in this study, we evaluated the potential and limitations of real-time species-level detection of thrips (\n                    <jats:italic>Frankliniella occidentalis<\/jats:italic>\n                    and\n                    <jats:italic>Echinothrips americanus<\/jats:italic>\n                    ) and whiteflies (\n                    <jats:italic>Bemisia tabaci<\/jats:italic>\n                    and\n                    <jats:italic>Trialeurodes vaporariorum<\/jats:italic>\n                    ) using non-microscopic, RGB yellow sticky trap images and recent YOLO-based deep learning detection models. To this end, a balanced and labelled image dataset was gathered, consisting of the studied pest species, caught on one type of yellow sticky trap. Subsequently, various versions of the YOLO11 and YOLO-NAS detection model architectures were trained and tested using this dataset at various (digitally reduced) pixel resolutions. All tested high-resolution dataset (pixel size: 5 \u00b5m) models achieved species-level detection of the studied pests on an independent test dataset (mAP@50: 79% - 89% | F1@50: 74% - 87%). Even the smallest model (YOLO11n) delivered feasible macro-averaged (mAP@50: 80% | F1@50: 77%) and classwise performance scores (AP@50: 72% - 85% | F1@50: 68% - 82%). The minimum required pixel resolution for feasible species-level detection in greenhouse horticulture was identified as 80\n                    <jats:italic>\u00b5m<\/jats:italic>\n                    for both the YOLO11n and YOLO11x models, enabling the use of modern smartphones, action cameras, or low-cost standalone camera modules. Combined with the low complexity and decent performance of the YOLO11n model, these results demonstrate the potential of feasible, real-time, automated species-level monitoring of (yellow) sticky traps in greenhouse horticulture. Future research should focus on extending this technology to additional pest species, sticky trap types, and ambient light conditions.\n                  <\/jats:p>","DOI":"10.3389\/fpls.2025.1668795","type":"journal-article","created":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T07:10:08Z","timestamp":1763449808000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["Species-level detection of thrips and whiteflies on yellow sticky traps using YOLO-based deep learning detection models"],"prefix":"10.3389","volume":"16","author":[{"given":"Broes","family":"Laekeman","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jochem","family":"Bonte","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wannes","family":"Dermauw","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Annelies","family":"Christiaens","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bruno","family":"Gobin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Johan","family":"Van Huylenbroeck","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emmy","family":"Dhooghe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter","family":"Lootens","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,11,18]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.10798312","article-title":"Deci-AI\/super-gradients: 3.6.1","author":"Aharon","year":"2024","journal-title":"Zenodo"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.3390\/computers13120336","article-title":"The yolo framework: A comprehensive review of evolution, applications, and benchmarks in object detection","volume":"13","author":"Ali","year":"2024","journal-title":"Computers"},{"key":"B3","doi-asserted-by":"publisher","first-page":"773","DOI":"10.17660\/ACTAHORTIC.2005.691.95","article-title":"Prototype of a vision based system for measurements of white fly infestation","volume":"691","author":"Bauch","year":"2005","journal-title":"Acta Hortic."},{"key":"B4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-021-89930-w","article-title":"Rapid and low-cost insect detection for analysing species trapped on yellow sticky traps","volume":"11","author":"B\u00f6ckmann","year":"2021","journal-title":"Sci. Rep."},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1016\/J.IBMB.2023.104068","article-title":"SYNCAS: Efficient CRISPR\/Cas9 gene-editing in difficult to transform arthropods","volume":"165","author":"De Rouck","year":"2024","journal-title":"Insect Biochem. Mol. Biol."},{"key":"B6","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1016\/J.COMPAG.2016.07.008","article-title":"Combination of image processing and artificial neural networks as a novel approach for the identification of Bemisia tabaci and Frankliniella occidentalis on sticky traps in greenhouse agriculture","volume":"127","author":"Espinoza","year":"2016","journal-title":"Comput. Electron. Agric."},{"key":"B7","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1111\/j.1365-2338.2004.00729.x","article-title":"Bemisia tabaci","volume":"34","year":"2004","journal-title":"EPPO Bull."},{"key":"B8","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1094\/PHYTO-07-19-0273-FI","article-title":"Transmission of begomoviruses and other whitefly-borne viruses: dependence on the vector species","volume":"110","author":"Fiallo-Oliv\u00e9","year":"2019","journal-title":"Phytopathology"},{"key":"B9","unstructured":"Plant Production and Protection\n          \n          2024"},{"key":"B10","unstructured":"Gula\n              L. T.\n            \n          \n          Researchers Helping Protect Crops From Pests\n          \n          2023"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1155\/2019\/5219471","article-title":"A benchmarking of learning strategies for pest detection and identification on tomato plants for autonomous scouting robots using internal databases","volume":"2019","author":"Gutierrez","year":"2019","journal-title":"J. Sensors"},{"key":"B12","doi-asserted-by":"publisher","first-page":"322","DOI":"10.1093\/EE\/21.2.322","article-title":"Sex ratio patterns and population dynamics of western flower thrips (Thysanoptera: thripidae)","volume":"21","author":"Higgins","year":"1992","journal-title":"Environ. Entomology"},{"key":"B13","doi-asserted-by":"publisher","first-page":"2585","DOI":"10.1007\/s10115-021-01605-0","article-title":"Model complexity of deep learning: A survey","volume":"63","author":"Hu","year":"2021","journal-title":"Knowledge Inf. Syst."},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2411.00201","article-title":"Yolo evolution: A comprehensive benchmark and architectural review of yolov12, yolo11, and their previous versions","author":"Jegham","year":"2024"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.14601862","article-title":"Ultralytics YOLO","author":"Jocher","year":"2025","journal-title":"Zenodo"},{"key":"B16","doi-asserted-by":"publisher","first-page":"e0213946","DOI":"10.1371\/JOURNAL.PONE.0213946","article-title":"Global genetic diversity and geographical distribution of Bemisia tabaci and its bacterial endosymbionts","volume":"14","author":"Kanakala","year":"2019","journal-title":"PloS One"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1016\/J.COMPAG.2021.106048","article-title":"Field detection of tiny pests from sticky trap images using deep learning in agricultural greenhouse","volume":"183","author":"Li","year":"2021","journal-title":"Comput. Electron. Agric."},{"key":"B18","doi-asserted-by":"publisher","first-page":"161","DOI":"10.3390\/AGRICULTURE10050161","article-title":"Automatic detection and monitoring of insect pests\u2014A review","volume":"10","author":"Lima","year":"2020","journal-title":"Agric. (Switzerland)"},{"key":"B19","doi-asserted-by":"publisher","first-page":"45301","DOI":"10.1109\/ACCESS.2019.2909522","article-title":"PestNet: an end-to-end deep learning approach for large-scale multi-class pest detection and classification","volume":"7","author":"Liu","year":"2019","journal-title":"IEEE Access"},{"key":"B20","volume-title":"What are thrips?","author":"Manners","year":"2017"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1016\/J.IBMB.2024.104232","article-title":"SYNCAS based CRISPR-Cas9 gene editing in predatory mites, whiteflies and stinkbugs","volume":"177","author":"Mocchetti","year":"2025","journal-title":"Insect Biochem. Mol. Biol."},{"key":"B22","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1146\/annurev.ento.49.061802.123318","article-title":"Thysanoptera-diversity and interactions","volume":"50","author":"Mound","year":"2005","journal-title":"Article Annu. Rev. Entomology"},{"key":"B23","doi-asserted-by":"crossref","first-page":"999","DOI":"10.1016\/B978-0-12-374144-8.00263-0","article-title":"Chapter 254 - Thysanoptera","volume-title":"Encyclopedia of insects","author":"Mound","year":"2009"},{"key":"B24","article-title":"Thysanoptera Britannica et Hibernica \u2013 Thrips of the British Isles","author":"Mound","year":"2025"},{"key":"B25","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-1-4899-1409-5_1","article-title":"\u201cThysanoptera as phytophagous opportunists,\u201d","author":"Mound","year":"1995","journal-title":"Thrips Biology and Management, 1st ed"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.3390\/INSECTS13010061","article-title":"Problems with the concept of \u201cPest\u201d among the diversity of pestiferous thrips","volume":"13","author":"Mound","year":"2022","journal-title":"Insects"},{"key":"B27","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1146\/annurev-phyto-072910-095235","article-title":"Emerging virus diseases transmitted by whiteflies","volume":"49","author":"Navas-Castillo","year":"2011","journal-title":"Annu. Rev. Phytopathol."},{"key":"B28","article-title":"In search of the real inductive bias: On the role of implicit regularization in deep learning","author":"Neyshabur","year":"2014"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.3390\/INSECTS14060523","article-title":"Real-Time detection and classification of scirtothrips dorsalis on fruit crops with smartphone-Based deep learning system: preliminary results","volume":"14","author":"Niyigena","year":"2023","journal-title":"Insects"},{"key":"B30","article-title":"Sensitivity and generalization in neural networks: An empirical study","author":"Novak","year":"2018"},{"key":"B31","doi-asserted-by":"publisher","first-page":"654","DOI":"10.1002\/PS.8464","article-title":"Trap colour strongly affects the ability of deep learning models to recognize insect species in images of sticky traps","volume":"81","author":"Ong","year":"2025","journal-title":"Pest Manage. Sci."},{"key":"B32","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1016\/B978-0-12-802441-6.00004-8","article-title":"Chapter 4 - whiteflies: biology, ecology, and management","volume-title":"Sustainable management of arthropod pests of tomato","author":"Perring","year":"2018"},{"key":"B33","unstructured":"Pijnakker\n              J.\n            \n            \n              Leman\n              A.\n            \n            \n              Vangansbeke\n              D.\n            \n            \n              W\u00e4ckers\n              F.\n            \n          \n          Echinothrips americanus: a bottleneck for integrated pest management ornamentals\n          \n          2018"},{"key":"B34","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1007\/s10340-020-01309-4","article-title":"Insect pest monitoring with camera-equipped traps: strengths and limitations","volume":"94","author":"Preti","year":"2021","journal-title":"J. Pest Sci."},{"key":"B35","volume-title":"Integrated Pest Management Program Echinothrips americanus","author":"Pundt","year":"2024"},{"key":"B36","doi-asserted-by":"publisher","first-page":"I1","DOI":"10.1603\/IPM10020","article-title":"Thrips vectors of tospoviruses","volume":"2","author":"Riley","year":"2011","journal-title":"J. Integrated Pest Manage."},{"key":"B37","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1016\/J.BIOSYSTEMSENG.2016.11.001","article-title":"A smart-vision algorithm for counting whiteflies and thrips on sticky traps using two-dimensional Fourier transform spectrum","volume":"153","author":"Sun","year":"2017","journal-title":"Biosyst. Eng."},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.3390\/AGRICULTURE13030713","article-title":"A systematic review on automatic insect detection using deep learning","volume":"13","author":"Teixeira","year":"2023","journal-title":"Agriculture"},{"key":"B39","doi-asserted-by":"publisher","first-page":"1680","DOI":"10.3390\/MAKE5040083","article-title":"A comprehensive review of YOLO architectures in computer vision: from YOLOv1 to YOLOv8 and YOLO-NAS","volume":"5","author":"Terven","year":"2023","journal-title":"Mach. Learn. Knowledge Extraction"},{"key":"B40","doi-asserted-by":"publisher","first-page":"71","DOI":"10.3000\/17252555.L_2009.309.eng","article-title":"Directive 2009\/128\/ec of the European parliament and of the council of 21 October 2009 establishing a framework for community action to achieve the sustainable use of pesticides","volume":"309","year":"2009","journal-title":"Official Journal of the European Union"},{"key":"B41","volume-title":"World Population Prospects 2022: Summary of Results","year":"2022"},{"key":"B42","doi-asserted-by":"publisher","first-page":"494","DOI":"10.1038\/s43016-021-00322-9","article-title":"A meta-analysis of projected global food demand and population at risk of hunger for the period 2010\u20132050","volume":"2","author":"van Dijk","year":"2021","journal-title":"Nat. Food"},{"key":"B43","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1556\/aphyt.41.2006.3-4.11","article-title":"Spread of two thrips pests in Europe: Echinothrips americanus and Microcephalothrips abdominalis (Thysanoptera:Thripidae)","volume":"41","author":"Vierbergen","year":"2006","journal-title":"Acta Phytopathologica Entomologica Hungarica"},{"key":"B44","doi-asserted-by":"publisher","DOI":"10.3390\/AGRONOMY14122887","article-title":"A deep-learning-based detection method for small target tomato pests in insect traps","volume":"14","author":"Wang","year":"2024","journal-title":"Agronomy"},{"key":"B45","doi-asserted-by":"publisher","first-page":"919","DOI":"10.13031\/TRANS.14394","article-title":"Using an improved YOLOv4 deep learning network for accurate detection of whitefly and thrips on sticky trap images","volume":"64","author":"Wang","year":"2021","journal-title":"Trans. ASABE"},{"key":"B46","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2024.3403191","article-title":"Thrips detection and monitoring system in mango greenhouses based on deep learning image recognition","volume":"73","author":"Wu","year":"2024","journal-title":"IEEE Trans. Instrumentation Measurement"},{"key":"B47","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1016\/J.ECOINF.2014.09.006","article-title":"Automatic identification and counting of small size pests in greenhouse conditions with low computational cost","volume":"29","author":"Xia","year":"2015","journal-title":"Ecol. Inf."},{"key":"B48","doi-asserted-by":"publisher","DOI":"10.3389\/FPLS.2023.1255719","article-title":"Automatic pest identification system in the greenhouse based on deep learning and machine vision","volume":"14","author":"Zhang","year":"2023","journal-title":"Front. Plant Sci."}],"container-title":["Frontiers in Plant Science"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2025.1668795\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T07:10:12Z","timestamp":1763449812000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2025.1668795\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,18]]},"references-count":48,"alternative-id":["10.3389\/fpls.2025.1668795"],"URL":"https:\/\/doi.org\/10.3389\/fpls.2025.1668795","relation":{"has-part":[{"id-type":"doi","id":"https:\/\/doi.org\/10.3389\/fpls.2025.1668795.s001","asserted-by":"subject"}]},"ISSN":["1664-462X"],"issn-type":[{"value":"1664-462X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,18]]},"article-number":"1668795"}}